A Multichannel Deep Neural Network Model Analyzing Multiscale Functional Brain Connectome Data for Attention Deficit Hyperactivity Disorder Detection

Published Online:https://doi.org/10.1148/ryai.2019190012

By fusing the multiscale brain connectome data, the multichannel deep neural network model improved attention deficit hyperactivity disorder detection performance considerably compared with the use of a single scale.

Purpose

To develop a multichannel deep neural network (mcDNN) classification model based on multiscale brain functional connectome data and demonstrate the value of this model by using attention deficit hyperactivity disorder (ADHD) detection as an example.

Materials and Methods

In this retrospective case-control study, existing data from the Neuro Bureau ADHD-200 dataset consisting of 973 participants were used. Multiscale functional brain connectomes based on both anatomic and functional criteria were constructed. The mcDNN model used the multiscale brain connectome data and personal characteristic data (PCD) as joint features to detect ADHD and identify the most predictive brain connectome features for ADHD diagnosis. The mcDNN model was compared with single-channel deep neural network (scDNN) models and the classification performance was evaluated through cross-validation and hold-out validation with the metrics of accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).

Results

In the cross-validation, the mcDNN model using combined features (fusion of the multiscale brain connectome data and PCD) achieved the best performance in ADHD detection with an AUC of 0.82 (95% confidence interval [CI]: 0.80, 0.83) compared with scDNN models using the features of the brain connectome at each individual scale and PCD, independently. In the hold-out validation, the mcDNN model achieved an AUC of 0.74 (95% CI: 0.73, 0.76).

Conclusion

An mcDNN model was developed for multiscale brain functional connectome data, and its utility for ADHD detection was demonstrated. By fusing the multiscale brain connectome data, the mcDNN model improved ADHD detection performance considerably over the use of a single scale.

© RSNA, 2019

References

  • 1. Glasser MF, Smith SM, Marcus DS et al. The Human Connectome Project’s neuroimaging approach. Nat Neurosci 2016;19(9):1175–1187. Crossref, MedlineGoogle Scholar
  • 2. Sporns O. The human connectome: origins and challenges. Neuroimage 2013;80:53–61. Crossref, MedlineGoogle Scholar
  • 3. Tzourio-Mazoyer N, Landeau B, Papathanassiou D et al. Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain. Neuroimage 2002;15(1):273–289. Crossref, MedlineGoogle Scholar
  • 4. Craddock RC, James GA, Holtzheimer PE 3rd, Hu XP, Mayberg HS. A whole brain fMRI atlas generated via spatially constrained spectral clustering. Hum Brain Mapp 2012;33(8):1914–1928. Crossref, MedlineGoogle Scholar
  • 5. Glasser MF, Coalson TS, Robinson EC et al. A multi-modal parcellation of human cerebral cortex. Nature 2016;536(7615):171–178. Crossref, MedlineGoogle Scholar
  • 6. Betzel RF, Bassett DS. Multi-scale brain networks. Neuroimage 2017;160:73–83. Crossref, MedlineGoogle Scholar
  • 7. Riaz A, Asad M, Alonso E, Slabaugh G. Fusion of fMRI and non-imaging data for ADHD classification. Comput Med Imaging Graph 2018;65:115–128. Crossref, MedlineGoogle Scholar
  • 8. He L, Li H, Holland SK, Yuan W, Altaye M, Parikh NA. Early prediction of cognitive deficits in very preterm infants using functional connectome data in an artificial neural network framework. Neuroimage Clin 2018;18:290–297. Crossref, MedlineGoogle Scholar
  • 9. dos Santos Siqueira A, Biazoli Junior CE, Comfort WE, Rohde LA, Sato JR. Abnormal functional resting-state networks in ADHD: graph theory and pattern recognition analysis of fMRI data. BioMed Res Int 2014;2014:380531. Crossref, MedlineGoogle Scholar
  • 10. Sidhu GS, Asgarian N, Greiner R, Brown MR. Kernel principal component analysis for dimensionality reduction in fMRI-based diagnosis of ADHD. Front Syst Neurosci 2012;6:74. Crossref, MedlineGoogle Scholar
  • 11. Fair DA, Nigg JT, Iyer S et al. Distinct neural signatures detected for ADHD subtypes after controlling for micro-movements in resting state functional connectivity MRI data. Front Syst Neurosci 2013;6:80. Crossref, MedlineGoogle Scholar
  • 12. Biederman J. Attention-deficit/hyperactivity disorder: a selective overview. Biol Psychiatry 2005;57(11):1215–1220. Crossref, MedlineGoogle Scholar
  • 13. American Psychiatric Association. Diagnostic and statistical manual of mental disorders. 5th ed. Washington, DC: American Psychiatric Publishing, 2013. CrossrefGoogle Scholar
  • 14. Zhu CZ, Zang YF, Cao QJ et al. Fisher discriminative analysis of resting-state brain function for attention-deficit/hyperactivity disorder. Neuroimage 2008;40(1):110–120. Crossref, MedlineGoogle Scholar
  • 15. Sen B, Borle NC, Greiner R, Brown MRG. A general prediction model for the detection of ADHD and Autism using structural and functional MRI. PLoS One 2018;13(4):e0194856. Crossref, MedlineGoogle Scholar
  • 16. Ambastha AK, Leong TYAlzheimer’s Disease Neuroimaging Initiative. A deep learning approach to neuroanatomical characterisation of Alzheimer’s disease. Stud Health Technol Inform 2017;245:1249. MedlineGoogle Scholar
  • 17. Li H, Parikh NA, He L. A novel transfer learning approach to enhance deep neural network classification of brain functional connectomes. Front Neurosci 2018;12:491. Crossref, MedlineGoogle Scholar
  • 18. Brown MR, Sidhu GS, Greiner R et al. ADHD-200 Global Competition: diagnosing ADHD using personal characteristic data can outperform resting state fMRI measurements. Front Syst Neurosci 2012;6:69. Crossref, MedlineGoogle Scholar
  • 19. van den Heuvel OA, van Wingen G, Soriano-Mas C et al. Brain circuitry of compulsivity. Eur Neuropsychopharmacol 2016;26(5):810–827. Crossref, MedlineGoogle Scholar
  • 20. Zalesky A, Fornito A, Harding IH et al. Whole-brain anatomical networks: does the choice of nodes matter? Neuroimage 2010;50(3):970–983. Crossref, MedlineGoogle Scholar
  • 21. Desikan RS, Ségonne F, Fischl B et al. An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest. Neuroimage 2006;31(3):968–980. Crossref, MedlineGoogle Scholar
  • 22. Diez I, Bonifazi P, Escudero I et al. A novel brain partition highlights the modular skeleton shared by structure and function. Sci Rep 2015;5(1):10532. Crossref, MedlineGoogle Scholar
  • 23. HD-200 Consortium. The ADHD-200 Consortium: a model to advance the translational potential of neuroimaging in clinical neuroscience. Front Syst Neurosci 2012;6:62. MedlineGoogle Scholar
  • 24. Bellec, P, Chu, C, Chouinard-Decorte, F, Benhajali, Y, Margulies, DS, Craddock, RC. The neuro bureau adhd-200 preprocessed repository. Neuroimage 2017;144:275–286. Crossref, MedlineGoogle Scholar
  • 25. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015;521(7553):436–444. Crossref, MedlineGoogle Scholar
  • 26. Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv:1412.6980. [preprint] https://arxiv.org/abs/1412.6980. Posted December 22, 2014. Revised January 30, 2017. Accessed October 5, 2018. Google Scholar
  • 27. Simonyan K, Vedaldi A, Zisserman A. Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv 1312.6034. [preprint] https://arxiv.org/abs/1312.6034 Posted December 20, 2013. Revised April 19, 2014. Accessed June 12, 2018. Google Scholar
  • 28. Fei F, Jie B, Zhang D. Frequent and discriminative subnetwork mining for mild cognitive impairment classification. Brain Connect 2014;4(5):347–360. Crossref, MedlineGoogle Scholar
  • 29. Khazaee A, Ebrahimzadeh A, Babajani-Feremi A. Application of advanced machine learning methods on resting-state fMRI network for identification of mild cognitive impairment and Alzheimer’s disease. Brain Imaging Behav 2016;10(3):799–817. Crossref, MedlineGoogle Scholar
  • 30. Wee CY, Yap PT, Shen D. Diagnosis of autism spectrum disorders using temporally distinct resting-state functional connectivity networks. CNS Neurosci Ther 2016;22(3):212–219. Crossref, MedlineGoogle Scholar
  • 31. Dey S, Rao AR, Shah M. Attributed graph distance measure for automatic detection of attention deficit hyperactive disordered subjects. Front Neural Circuits 2014;8:64. Crossref, MedlineGoogle Scholar
  • 32. Tafazoli S, O’Neill J, Bejjani A et al. 1H MRSI of middle frontal gyrus in pediatric ADHD. J Psychiatr Res 2013;47(4):505–512. Crossref, MedlineGoogle Scholar
  • 33. Valera EM, Spencer RM, Zeffiro TA et al. Neural substrates of impaired sensorimotor timing in adult attention-deficit/hyperactivity disorder. Biol Psychiatry 2010;68(4):359–367. Crossref, MedlineGoogle Scholar
  • 34. Tian L, Jiang T, Liang M et al. Enhanced resting-state brain activities in ADHD patients: a fMRI study. Brain Dev 2008;30(5):342–348. Crossref, MedlineGoogle Scholar
  • 35. Kaczkurkin AN, Raznahan A, Satterthwaite TD. Sex differences in the developing brain: insights from multimodal neuroimaging. Neuropsychopharmacology 2019;44(1):71–85. Crossref, MedlineGoogle Scholar
  • 36. Bengio Y. Learning deep architectures for AI. Found Trends Mach Learn 2009;2(1):1–127. CrossrefGoogle Scholar

Article History

Received: Feb 11 2019
Revision requested: Mar 26 2019
Revision received: July 18 2019
Accepted: July 25 2019
Published online: Dec 11 2019